The WebNN CPU device type may now target different backends, such as
CoreML. Legacy special workarounds for the TFLite backend should be
removed and allowed to fail as is, as these are implementation issues.
Additionally, the WebNN EP should adhere to the WebNN API conformance.
We assume all the WebNN ops should be supported, so remove the WebNN op
support status for different device types in webnn-operators.md as well.
WebNN doesn't provide a dedicated op for RotaryEmbedding. Instead, we
implement it by using a combination of WebNN ops. The decomposed graph
is referenced from DML EP at:
onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/DmlOperatorRotaryEmbedding.cpp
The algorithm of `SkipSimplifiedLayerNormalization` is quite similar to
the `SimplifiedLayerNormalization`, only different is
`SkipSimplifiedLayerNormalization` provides an additional output used
for calculating the sum of the input, skip and bias (if it exits).
BTW, fix a bug in `SimplifiedLayerNormalization`, adding bias if it
exits.
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
WebNN doesn't provide dedicate op for LRN, use a couple of WebNN ops to
emulate it in WebNN EP:
pow -> transpose -> pad -> averagePool -> transpose -> mul -> add -> pow
-> div
@Honry @fdwr PTAL, thanks!
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
WebNN doesn't provide dedicate op for SimplifiedLayerNormalization, use
a couple of WebNN ops to emulate it in WebNN EP.
X --> Pow --> ReduceMean --> Add --> Sqrt --> Div -> Mul
<!-- Describe your changes. -->
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
<!-- Describe your changes. -->
#21618
With this PR, the cross device copying (`MemcpyToHost`) can totally be
removed for model `wav2vec2`. And the overall time becomes 48ms from
604ms.
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
Added DequantizeLinear operator for JSEP.
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
WebNN only supports test mode, so we don't care about other inputs or
attributes about training mode, use WebNN's identity op to implement the
Dropout op directly.
WebNN spec recently changes the definition of argMax/argMin:
- Remove selectLastIndex option, let backends decide to select the last
index or not.
- Move axes option to axis input
Currently WebNN TFLite backend allows the filter of
conv2d/convTranspose2d be an input. Remove the constraint and operate
necessary transpose/reshape operations for the filter input.
WebNN CPU implementation has been migrated from XNNPack to TFLite which
supports more ops. Turn on partial `cpu` supported ops which just need
the change from `false` to `true` firstly.
Following constraints have been supported by WebNN TFLite backend:
- Concat: supports up to 4 inputs
- Matmul: supports broadcasting
- Resize: supports nearest mode
- Split: supports up to 4 outputs
WebNN CPU backend implementation has been migrated from XNNPack to
TFLite, currently TFLite has not supported WebNN's convTranspose2d yet,
just disable it for now.
